from bokeh.models import ColumnDataSource, HoverTool, LinearColorMapper, CustomJS
from bokeh.palettes import Category20
from bokeh.transform import linear_cmap
from bokeh.io import output_file, show
from bokeh.transform import transform
from bokeh.io import output_notebook
from bokeh.plotting import figure
from bokeh.layouts import column
from bokeh.models import RadioButtonGroup
from bokeh.models import TextInput
from bokeh.layouts import gridplot
from bokeh.models import Div
from bokeh.models import Paragraph
from bokeh.layouts import column, widgetbox
output_notebook()
y_labels = y_pred
# data sources
source = ColumnDataSource(data=dict(
x= X_embedded[:,0],
y= X_embedded[:,1],
x_backup = X_embedded[:,0],
y_backup = X_embedded[:,1],
desc= y_labels,
titles= df_covid['title'],
authors = df_covid['authors'],
journal = df_covid['journal'],
abstract = df_covid['abstract_summary'],
labels = ["C-" + str(x) for x in y_labels]
))
# hover over information
hover = HoverTool(tooltips=[
("Title", "@titles{safe}"),
("Author(s)", "@authors"),
("Journal", "@journal"),
("Abstract", "@abstract{safe}"),
],
point_policy="follow_mouse")
# map colors
mapper = linear_cmap(field_name='desc',
palette=Category20[20],
low=min(y_labels) ,high=max(y_labels))
# prepare the figure
p = figure(plot_width=800, plot_height=800,
tools=[hover, 'pan', 'wheel_zoom', 'box_zoom', 'reset'],
title="t-SNE Covid-19 Articles, Clustered(K-Means), Tf-idf with Plain Text",
toolbar_location="right")
# plot
p.scatter('x', 'y', size=5,
source=source,
fill_color=mapper,
line_alpha=0.3,
line_color="black",
legend = 'labels')
# add callback to control
callback = CustomJS(args=dict(p=p, source=source), code="""
var radio_value = cb_obj.active;
var data = source.data;
x = data['x'];
y = data['y'];
x_backup = data['x_backup'];
y_backup = data['y_backup'];
labels = data['desc'];
if (radio_value == '20') {
for (i = 0; i < x.length; i++) {
x[i] = x_backup[i];
y[i] = y_backup[i];
}
}
else {
for (i = 0; i < x.length; i++) {
if(labels[i] == radio_value) {
x[i] = x_backup[i];
y[i] = y_backup[i];
} else {
x[i] = undefined;
y[i] = undefined;
}
}
}
source.change.emit();
""")
# callback for searchbar
keyword_callback = CustomJS(args=dict(p=p, source=source), code="""
var text_value = cb_obj.value;
var data = source.data;
x = data['x'];
y = data['y'];
x_backup = data['x_backup'];
y_backup = data['y_backup'];
abstract = data['abstract'];
titles = data['titles'];
authors = data['authors'];
journal = data['journal'];
for (i = 0; i < x.length; i++) {
if(abstract[i].includes(text_value) ||
titles[i].includes(text_value) ||
authors[i].includes(text_value) ||
journal[i].includes(text_value)) {
x[i] = x_backup[i];
y[i] = y_backup[i];
} else {
x[i] = undefined;
y[i] = undefined;
}
}
source.change.emit();
""")
# option
option = RadioButtonGroup(labels=["C-0", "C-1", "C-2",
"C-3", "C-4", "C-5",
"C-6", "C-7", "C-8",
"C-9", "C-10", "C-11",
"C-12", "C-13", "C-14",
"C-15", "C-16", "C-17",
"C-18", "C-19", "All"],
active=20)#, callback=callback)
# search box
keyword = TextInput(title="Search:")#, callback=keyword_callback)
#header
header = Div(text="""<h1>COVID-19 Literature Cluster</h1>""")
# show
show(column(header, widgetbox(option, keyword),p))
